Segmentation of finger tendon and synovial sheath in ultrasound image using deep convolutional neural network

Abstract

Background: Trigger finger is a common hand disease, which is caused by a mismatch in diameter between the tendon and the pulley. Ultrasound images are typically used to diagnose this disease, which are also used to guide surgical treatment. However, background noise and unclear tissue boundaries in the images increase the difficulty of the process. To overcome these problems, a computer-aided tool for the identification of finger tissue is needed.

Results: Two datasets were used for evaluation: one comprised different cases of individual images and another consisting of eight groups of continuous images. Regarding result similarity and contour smoothness, our proposed deeply supervised dilated fully convolutional DenseNet (D2FC-DN) is better than ATASM (the state-of-art segmentation method) and representative CNN methods. As a practical application, our proposed method can be used to build a tendon and synovial sheath model that can be used in a training system for ultrasound-guided trigger finger surgery.

Conclusion: We proposed a D2FC-DN for finger tendon and synovial sheath segmentation in ultrasound images. The segmentation results were remarkably accurate for two datasets. It can be applied to assist the diagnosis of trigger finger by highlighting the tissues and generate models for surgical training systems in the future.

Methods: We propose a novel finger tendon segmentation method for use with ultrasound images that can also be used for synovial sheath segmentation that yields a more complete description for analysis. In this study, a hybrid of effective convolutional neural network techniques are applied, resulting in a deeply supervised dilated fully convolutional DenseNet (D2FC-DN), which displayed excellent segmentation performance on the tendon and synovial sheath.

Keywords: Convolutional neural network; Segmentation; Synovial sheath; Tendon; Trigger finger; Ultrasound images.

Fig. 1

Ultrasound image of the tendon and synovial sheath of a finger. a Original image acquired around A1 pulley. b Tendon (solid line), synovial sheath (dotted line) area, and surrounding tissues

Fig. 2

Dataset image samples. a, b Chuang’s dataset; c, d MB dataset

Fig. 3

Predicted result contours (cyan) and the convex hull outputs (red). a Smooth contour (CHD = 1.41). b Contour with a bud (CHD = 7.62). c Contour with a groove (CHD = 18.68)

Fig. 4

Segmentation results of tendon on Chuang’s dataset

Fig. 5

Segmentation results of synovial sheath on Chuang’s dataset

Fig. 6

Segmentation results of tendon and synovial sheath images

Fig. 7

3D tendon model of MB dataset

Fig. 8

3D synovial sheath model of MB dataset

Fig. 9

CHD results of Chuang’s dataset. a Tendon, b synovial sheath

Fig. 10

CHD results of MB dataset. a Tendon, b synovial sheath. *Method (group#)

Fig. 11

The architecture of U-Net

Fig. 12

The architecture of FC-DenseNet

Fig. 13

A dense block with four layers

Fig. 14

Dilated convolution with different dilation factors

Fig. 15

Original and dilated dense block layers. a Original, b dilated

Fig. 16

Proposed segmentation network